Commit
•
14e45a6
1
Parent(s):
14bd0b4
Training in progress, epoch 4, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 498615900
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:161429549ad046c92c0830348f3519a81c9695140c076ba86819b63651deff64
|
3 |
size 498615900
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 997351674
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:303573cf617fd5524986ae8dd755826ae69c14b6d66df9a27c6e00700c7f2ce6
|
3 |
size 997351674
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47899d438bc1e8e9d368d92fe5b1946e59435e7701dd92edc87bdef54734dd67
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11342b2430a338f69f1320c6f8235ca7935daec91992c25666791c4e55f7a3d9
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "training_dir/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -64,6 +64,25 @@
|
|
64 |
"eval_samples_per_second": 46.846,
|
65 |
"eval_steps_per_second": 5.856,
|
66 |
"step": 750
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
}
|
68 |
],
|
69 |
"logging_steps": 500,
|
@@ -83,7 +102,7 @@
|
|
83 |
"attributes": {}
|
84 |
}
|
85 |
},
|
86 |
-
"total_flos":
|
87 |
"train_batch_size": 8,
|
88 |
"trial_name": null,
|
89 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6211330799726014,
|
3 |
+
"best_model_checkpoint": "training_dir/checkpoint-1000",
|
4 |
+
"epoch": 4.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
64 |
"eval_samples_per_second": 46.846,
|
65 |
"eval_steps_per_second": 5.856,
|
66 |
"step": 750
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 4.0,
|
70 |
+
"grad_norm": 61.78361129760742,
|
71 |
+
"learning_rate": 4.5e-05,
|
72 |
+
"loss": 0.4837,
|
73 |
+
"step": 1000
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 4.0,
|
77 |
+
"eval_accuracy": 0.6359265734265734,
|
78 |
+
"eval_f1": 0.6211330799726014,
|
79 |
+
"eval_loss": 1.4274829626083374,
|
80 |
+
"eval_precision": 0.6772601484892057,
|
81 |
+
"eval_recall": 0.6359265734265734,
|
82 |
+
"eval_runtime": 48.713,
|
83 |
+
"eval_samples_per_second": 46.969,
|
84 |
+
"eval_steps_per_second": 5.871,
|
85 |
+
"step": 1000
|
86 |
}
|
87 |
],
|
88 |
"logging_steps": 500,
|
|
|
102 |
"attributes": {}
|
103 |
}
|
104 |
},
|
105 |
+
"total_flos": 1668780407351232.0,
|
106 |
"train_batch_size": 8,
|
107 |
"trial_name": null,
|
108 |
"trial_params": null
|